CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection

TL;DR

CLOCs is a novel fusion network that combines camera and LiDAR object candidates to significantly enhance 3D object detection accuracy, especially at long distances, outperforming existing fusion methods on the KITTI benchmark.

Contribution

The paper introduces CLOCs, a low-complexity multi-modal fusion framework that improves detection performance by leveraging geometric and semantic consistencies before NMS.

Findings

Significant performance improvements on KITTI benchmark.

Outperforms state-of-the-art fusion methods.

Ranks highest among fusion-based methods in KITTI leaderboard.

Abstract

There have been significant advances in neural networks for both 3D object detection using LiDAR and 2D object detection using video. However, it has been surprisingly difficult to train networks to effectively use both modalities in a way that demonstrates gain over single-modality networks. In this paper, we propose a novel Camera-LiDAR Object Candidates (CLOCs) fusion network. CLOCs fusion provides a low-complexity multi-modal fusion framework that significantly improves the performance of single-modality detectors. CLOCs operates on the combined output candidates before Non-Maximum Suppression (NMS) of any 2D and any 3D detector, and is trained to leverage their geometric and semantic consistencies to produce more accurate final 3D and 2D detection results. Our experimental evaluation on the challenging KITTI object detection benchmark, including 3D and bird's eye view metrics, shows significant improvements, especially at long distance, over the state-of-the-art fusion based methods. At time of submission, CLOCs ranks the highest among all the fusion-based methods in the official KITTI leaderboard. We will release our code upon acceptance.